Issue of TiDB Cluster TiDB-Server CPU Being Fully Utilized

This topic has been translated from a Chinese forum by GPT and might contain errors.

Original topic: tidb集群 tidb-server cpu 打满问题

| username: TiDBer_pFFcXLgY

[TiDB Usage Environment] Production Environment
[TiDB Version] V5.1.3
[Encountered Problem: Phenomenon and Impact]
From the monitoring graph, the CPU suddenly maxed out, causing the machine to become unresponsive and only recoverable through a forced reboot.
Can the cause be identified after recovery?
No relevant logs were found through slow query logs and tidb.log.
[Resource Configuration]
CPU: 8C Memory: 16G
[Attachments: Screenshots/Logs/Monitoring]
Monitoring graph

tidb.log log

| username: xfworld | Original post link

  1. Upload the cluster configuration list.
  2. Was there any business operation before and after the CPU suddenly maxed out?
  3. After restarting, does it still recur?
| username: 胡杨树旁 | Original post link

Is there slow SQL when the CPU is fully utilized?

| username: Hacker_ufuLjDKs | Original post link

How large is the concurrent connection?
If the CPU on the tidb-server side is fully utilized, it could be genuinely busy or falsely busy.
It seems like yours is falsely busy, with the tidb-server waiting for tikv.

| username: TiDBer_pFFcXLgY | Original post link

There should be a large query.

| username: system | Original post link

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.